AgentTeamLandAI agent teams, installed like packages.

A package manager for curated teams of AI agents — install a stack, keep it current, ship.

📦

Teams as packages

A team bundles specialized agents, skills, and rules for a kind of work — full-stack apps, design systems, and more. Install once, copied into your project's Claude Code directory.

⚡

One static binary

atl is a ~18 MB Go binary with zero runtime dependencies. Install with a single curl (macOS/Linux) or PowerShell (Windows) command.

🔄

Self-driving updates + learning

Hooks keep your teams current and fold in-session learnings into their knowledge base automatically — promote gains to your global layer, publish them upstream.

🧪

A community catalog

No central gatekeeper — the catalog is generated from public GitHub repos tagged with the atl-team topic. Anything listed installs with one command.

🔍

Open self-publish

Tag your repo with the atl-team GitHub topic and run atl publish — no central gatekeeper. Discover any team by name with atl search.

🛠️

Open and scriptable

Every piece is MIT-licensed. team.json is a public schema. Build your own team and publish it.

See it in action

In 30 seconds

bash

# macOS / Linux
curl -fsSL https://raw.githubusercontent.com/agentteamland/atl/main/scripts/install.sh | sh

powershell

# Windows (PowerShell)
irm https://raw.githubusercontent.com/agentteamland/atl/main/scripts/install.ps1 | iex

bash

# Then, in any project:
atl install <handle>/<team>
atl setup-hooks                   # not required — atl install already binds the automation hooks (re-run only to re-bind or change --throttle)

The team's agents, skills, and rules are wired into your project's .claude/ directory, ready for Claude Code.

What's next?

What is atl? — the big idea in five minutes.
Quickstart — first team installed in under a minute.
Browse teams — how the catalog works and how to discover teams.
Team authoring — publish your own team.